paper-with-me

Papers

An Isotropy Analysis in the Multilingual BERT Embedding Space

2021-10-09 · Findings (ACL) 2022 5 · Sara Rajaee, Mohammad Taher Pilehvar

Several studies have explored various advantages of multilingual pre-trained models (such as multilingual BERT) in capturing shared linguistic knowledge. However, less attention has been paid to their limitations. In this paper, we investigate the multilingual BERT for two known issues of the monolingual models: anisotropic embedding space and outlier dimensions. We show that, unlike its monolingual counterpart, the multilingual BERT model exhibits no outlier dimension in its representations while it has a highly anisotropic space. There are a few dimensions in the monolingual BERT with high contributions to the anisotropic distribution. However, we observe no such dimensions in the multilingual BERT. Furthermore, our experimental results demonstrate that increasing the isotropy of multilingual space can significantly improve its representation power and performance, similarly to what had been observed for monolingual CWRs on semantic similarity tasks. Our analysis indicates that, despite having different degenerated directions, the embedding spaces in various languages tend to be partially similar with respect to their structures.

📄 PDF Abstract BibTeX arXiv:2110.04504

Code (1)

sara-rajaee/multilingual-isotropy 공식 구현

Tasks

Semantic SimilaritySemantic Textual Similarity

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
WordPiece 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

An Isotropy Analysis in the Multilingual BERT Embedding Space

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Several studies have explored various advantages of multilingual pre-trained models (e.g., multilingual BERT) in capturing shared linguistic knowledge. However, their limitations have not been paid enough attention to. I…

Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions

2021-07-19 · Haoran Xu, Philipp Koehn

Typically, a linearly orthogonal transformation mapping is learned by aligning static type-level embeddings to build a shared semantic space. In view of the analysis that contextual embeddings contain richer semantic fea…

Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity

2023-06-01 · Katharina Hämmerl, Alina Fastowski, Jindřich Libovický, Alexander Fraser

Previous work has shown that the representations output by contextual language models are more anisotropic than static type embeddings, and typically display outlier dimensions. This seems to be true for both monolingual…

Semantic SimilaritySemantic Textual SimilaritySentenceSentence Similarity

Hubness, Not Anisotropy, Drives Cross-Lingual Retrieval Asymmetry in Multilingual Embedding Models

2026-05-26 · Adib Sakhawat, Fardeen Sadab, Atik Shahriar arxiv

Multilingual embedding models are deployed under the assumption that cross-lingual retrieval is symmetric: if a query in language A retrieves its translation in language B, the reverse should also hold. In practice it do…

Isotropy-Optimized Contrastive Learning for Semantic Course Recommendation

2026-01-16 · Ali Khreis, Anthony Nasr, Yusuf Hilal arxiv

This paper presents a semantic course recommendation system for students using a self-supervised contrastive learning approach built upon BERT (Bidirectional Encoder Representations from Transformers). Traditional BERT e…

Contrastive LearningData Augmentation